import_data_from_local = FALSE # expects logical input

  file_name <- " " #enter the file name
  file_path <- " " #enter the path of the file in local.

# Loading the data in the Rstudio environment 
# Please change the path in the code line below to the path location of the .csv file
if(import_data_from_local){
  file_load <- paste0(file_path, file_name)
  dataset_updated <- as.data.frame(fread(file_load))
  if(nrow(dataset_updated) > 0){
    paste0("File ", file_name, " having ", nrow(dataset_updated), " row(s) and ", ncol(dataset_updated), " column(s)",  " imported successfully. ") %>% cat("\n")
    # Round only the numeric columns in dataset
    dataset_updated <- dataset_updated %>% mutate_if(is.numeric, round, digits = 4)
    paste0("Code chunk executed successfully. Below table showing first 10 row(s) of the dataset.") %>% cat("\n")
    # Display imported dataset
    dataset_updated %>% head(10) %>% 
      as.data.frame() %>%
      DT::datatable(options = options, rownames = TRUE)
  }
  
} 

calculate_statistics <- function(column_data) {
     if (is.numeric(column_data)) {
         a <- min(column_data, na.rm = TRUE)
         b <- as.numeric(quantile(column_data, probs = 0.25, na.rm = TRUE)[1])
         c <- median(column_data, na.rm = TRUE)
         d <- mean(column_data, na.rm = TRUE)
         e <- sd(column_data, na.rm = TRUE)
         f <- as.numeric(quantile(column_data, probs = 0.75, na.rm = TRUE)[1])
         g <- max(column_data, na.rm = TRUE)
         
         # Combine the statistics into a data frame and set row names to an empty string
         stats_data <- data.frame(Min = a, Q1 = b, Median = c, Mean = d, sd = e, Q3 = f, Max = g)
         row.names(stats_data) <- ""
     } else {
         cat("Column is not numeric and was skipped.\n")
         return(NULL)
     }
     return(stats_data)
 }

# Apply the function to each column of dataset_updated_train
statistics_list <- lapply(dataset_updated, calculate_statistics)

# Print the result
print(statistics_list)

dataset_updated %>% str()

########################################################################################
################################## User Input Needed ###################################
########################################################################################

# Add column names which you want to remove
want_to_delete_column <- "no"

    del_col<-c(" `column_name` ")  

if(want_to_delete_column == "yes"){
   dataset_updated <-  dataset_updated[ , !(names(dataset_updated) %in% del_col)]
  print("Code chunk executed successfully. Overview of data types after removed selected columns")
  str( dataset_updated)
}else{
  paste0("No Columns removed. Please enter column name if you want to remove that column") %>% cat("\n")
}

########################################################################################
################################## User Input Needed ###################################
########################################################################################

# convert the column names to lower case
colnames( dataset_updated) <- colnames( dataset_updated) %>% casefold()

## rename column ?
want_to_rename_column <- "no" ## type "yes" if you want to rename a column

## renaming a column of a dataset 
rename_col_name <- " 'column_name` " ## use small letters
rename_col_name_to <- " `new_name` "

if(want_to_rename_column == "yes"){
  names( dataset_updated)[names( dataset_updated) == rename_col_name] <- rename_col_name_to
}

# remove space, comma, dot from column names
spaceless <- function(x) {colnames(x) <- gsub(pattern = "[^[:alnum:]]+",
                             replacement = ".",
                             names(x));x}
 dataset_updated <- spaceless( dataset_updated)

## below is the dataset summary
paste0("Successfully converted the column names to lower case and check the renamed column name if you changed") %>% cat("\n")

str( dataset_updated) ## showing summary for updated 

########################################################################################
################################## User Input Needed ###################################
########################################################################################

# If you want to change column type, change a below variable value to "yes"
want_to_change_column_type <- "no"

# you can change column type into numeric or character only
change_column_to_type <- "character" ## numeric

if(want_to_change_column_type == "yes" && change_column_to_type == "character"){
########################################################################################
################################## User Input Needed ###################################
########################################################################################
  select_columns <- c("panel_var") ###### Add column names you want to change here #####
   dataset_updated[select_columns]<- sapply( dataset_updated[select_columns],as.character)
  paste0("Code chunk executed successfully. Datatype of selected column(s) have been changed into numerical.")
  #str( dataset_updated)
}else if(want_to_change_column_type == "yes" && change_column_to_type == "numeric"){
  select_columns <- c('gearbox_oil_temperature')
   dataset_updated[select_columns]<- sapply( dataset_updated[select_columns],as.numeric)
  paste0("Code chunk executed successfully. Datatype of selected column(s) have been changed into categorical.")
  #str( dataset_updated)
}else{
  paste0("Datatype of columns have not been changed.") %>% cat("\n")
}

dataset_updated <- do.call(data.frame, dataset_updated)
str( dataset_updated)

want_to_remove_duplicates <- "yes"  ## type "no" for choosing to not remove duplicates

## removing duplicate observation if present in the dataset
if(want_to_remove_duplicates == "yes"){
  
   dataset_updated <-  dataset_updated %>% unique()
  paste0("Code chunk executed successfully, duplicates if present successfully removed. Updated dataset has ", nrow( dataset_updated), " row(s) and ", ncol( dataset_updated), " column(s)") %>% print()
  cat("\n")
  str( dataset_updated) ## showing summary for updated dataset
} else{
  paste0("Code chunk executed successfully, NO duplicates were removed") %>% print()
}

# Return the column type 
CheckColumnType <- function(dataVector) {
  #Check if the column type is "numeric" or "character" & decide type accordingly
  if (class(dataVector) == "integer" || class(dataVector) == "numeric") {
    columnType <- "numeric"
  } else { columnType <- "character" }
  #Return the result
  return(columnType)
}
### Loading the list of numeric columns in variable
numeric_cols <<- colnames( dataset_updated)[unlist(sapply( dataset_updated, 
                                                       FUN = function(x){ CheckColumnType(x) == "numeric"}))]

### Loading the list of categorical columns in variable
cat_cols <- colnames( dataset_updated)[unlist(sapply( dataset_updated, 
                                                   FUN = function(x){ 
                                                     CheckColumnType(x) == "character"|| CheckColumnType(x) == "factor"}))]

### Removing Date Column from the list of categorical column
paste0("Code chunk executed successfully, list of numeric and categorical variables created.") %>% cat()

paste0("\n\n Numerical Column(s): \n Count : ", length(numeric_cols), "\n") %>% cat()

paste0(numeric_cols) %>% print()

paste0("\n Categorical Column(s): \n Count : ", length(cat_cols), "\n") %>% cat()

paste0(cat_cols) %>% print()

want_to_filter_dataset <- "no" ## type "yes" in case you want to filter
filter_col <- " "  ## Enter Column name to filter
filter_val <- " "        ## Enter Value to exclude for the column selected

if(want_to_filter_dataset == "yes"){
   dataset_updated <- filter_at( dataset_updated
                              , vars(contains(filter_col))
                              , all_vars(. != filter_val))
  
  paste0("Code chunk executed successfully, dataset filtered successfully on required columns. Updated dataset has ", nrow( dataset_updated), " row(s) and ", ncol( dataset_updated), " column(s)") %>% print()
  cat("\n")
  str( dataset_updated) ## showing summary for updated dataset
  
} else{
  paste0("Code chunk executed successfully, entire dataset is available for analysis.") %>% print()
}

na_total <- sum(is.na( dataset_updated))/prod(dim( dataset_updated))
if(na_total == 0){
  paste0("In the uploaded dataset, there is no missing value") %>% cat("\n")
}else{
  na_percentage <- paste0(sprintf(na_total*100, fmt = '%#.2f'),"%")
  paste0("Percentage of missing value in entire dataset is ",na_percentage) %>% cat("\n")
}

# Below code gives you missing value in each column
paste0("Number of missing value in each column") %>% cat("\n")

print(sapply( dataset_updated, function(x) sum(is.na(x))))

missing_col_names <- names(which(sapply( dataset_updated, anyNA)))

total_na <- sum(is.na( dataset_updated))
# visualize the missing values (if any) using bar chart
if(total_na > 0 && length(missing_col_names) > 1){
  paste0("Code chunk executed successfully. Visualizing the missing values using bar chart") %>% cat("\n")
  gg_miss_upset( dataset_updated,
  nsets = 10,
  nintersects = NA)
}else if(total_na > 0){
   dataset_updated %>%
  DataExplorer::plot_missing() 
  # paste0("Code chunk executed successfully. Only one column ",missing_col_names," have missing values ", sum(is.na( dataset_updated)),".") %>% cat("\n")
}else{
  paste("Code chunk executed successfully. No missing value exist.") %>% cat("\n")
}

########################################################################################
################################## User Input Needed ###################################
########################################################################################

# OR do you want to drop column specific column
drop_cloumn_name_na <- "yes" ## type "yes" to drop column(s)
# write column name that you want to drop
drop_column_name <- c(" ") #enter column name
if(drop_cloumn_name_na == "yes"){
  names_df=names( dataset_updated) %in% drop_column_name
  dataset_updated <-  dataset_updated[ , which(!names( dataset_updated) %in% drop_column_name)]
  paste0("Code chunk executed, selected column(s) dropped successfully.") %>% print()
  cat("\n")
  str( dataset_updated)
} else {
  paste0("Code chunk executed, missing value not removed (if any).") %>% cat("\n")
  cat("\n")
}

# Do you want to drop row(s) containing "NA"
drop_row <- "no" ## type "yes" to delete missing value observations
if(drop_row == "yes"){
  
  # imputing blank with NAs and removing all rows containing NAs
  #  dataset_updated[ dataset_updated == ""] <- NA
  # removing missing values from data
   dataset_updated <-  dataset_updated %>% na.omit()
  
  paste0("Code chunk executed, missing values successfully identified and removed. Updated dataset has ", nrow( dataset_updated), " row(s) and ", ncol( dataset_updated), " column(s)") %>% print()
  cat("\n")
  # str( dataset_updated)
  
} else{
  paste0("Code chunk executed, missing value(s) not removed (if any).") %>% cat("\n")
  cat("\n")
}

nums <- colnames(dataset_updated)[unlist(lapply(dataset_updated, is.numeric))]
cat(paste0("Final data frame contains ", nrow( dataset_updated), " row(s) and ", ncol( dataset_updated), " column(s).","Code chunk executed. Below table showing first 10 row(s) of the dataset."))

dataset_updated <-  dataset_updated %>% mutate_if(is.numeric, round, digits = 4)

dataset_updated %>% head(10) %>%
  as.data.frame() %>%
  Table(scroll = FALSE)

      DT::datatable(
        dataset_updated %>%
          select_if(., is.numeric) %>%
          skimr::skim() %>%
          mutate_if(is.numeric, round, digits = 4) %>%
          rename_at(.vars = vars(starts_with("skim_")), .funs = funs(sub("skim_", "", .))) %>%
          rename_at(.vars = vars(starts_with("numeric.")), .funs = funs(sub("numeric.", "", .))) %>%
          select(-c(type, n_missing, complete_rate)) %>%
          mutate(n_row = nrow(dataset_updated),
                 n_missing = rowSums(is.na(.))
                 # ,n_non_missing = n_row - n_missing
                 ) ,
        selection = "none",
        # filter = "top",
        class = 'cell-border stripe',
        escape = FALSE,
        options = options,
        callback = htmlwidgets::JS(
          "var tips = ['Index showing column number',
                        'Columns used for building the HVT model',
                        'Histogram for individual column',
                        'Number of records for each feature',
                        'Number of missing (NA) values for each feature',
                        'Mean of individual column',
                        'Standard deviation of individual column',
                        '0th Percentile means that the values are smaller than all 100% of the rows',
                        '25th Percentile means that the values are bigger than 25% and smaller than only 75% of the rows',
                        '50th Percentile means that the values are bigger than 50% and smaller than only 50% of the rows',
                        '75th Percentile means that the values are bigger than 75% and smaller than only 25% of the rows',
                        '100th Percentile means that the values are bigger than 100% of the rows'],
                            header = table.columns().header();
                        for (var i = 0; i < tips.length; i++) {
                          $(header[i]).attr('title', tips[i]);
                        }"
        )
      )

#print(
 aa <-  dataset_updated %>%
    select_if(., is.numeric) %>%
    skimr::skim() %>%
    mutate_if(is.numeric, round, digits = 4) %>%
    rename_at(.vars = vars(starts_with("skim_")), .funs = funs(sub("skim_", "", .))) %>%
    rename_at(.vars = vars(starts_with("numeric.")), .funs = funs(sub("numeric.", "", .))) %>%
    select(-c(type, n_missing, complete_rate)) %>%
    mutate(n_row = nrow(dataset_updated),
           n_missing = rowSums(is.na(.))
           # ,n_non_missing = n_row - n_missing
           )
Table(aa,scroll = TRUE, limit = 20)

eda_cols <- names(dataset_updated_train)
# Here we plot the distribution of columns selected by user for numerical transformation
dist_list <- lapply(1:length(eda_cols), function(i){
generateDistributionPlot(dataset_updated_train, eda_cols[i]) })
do.call(gridExtra::grid.arrange, args = list(grobs = dist_list, ncol = 2, top = "Distribution of Features"))

eda_cols <- names(dataset_updated_test)
# Here we plot the distribution of columns selected by user for numerical transformation
dist_list <- lapply(1:length(eda_cols), function(i){
generateDistributionPlot(dataset_updated_test, eda_cols[i]) })
do.call(gridExtra::grid.arrange, args = list(grobs = dist_list, ncol = 2, top = "Distribution of Features"))